Zero day attack vulnerabilities: mitigation using machine learning for performance evaluation

Idris Olanrewaju Ibraheem, Abdulrauf Uthman Tosho

Abstract


The paper explores and investigate how machine learning methods can help defend against zero-day cyber-attacks, which are a major concern in cybersecurity. The study focuses on several machine learning algorithms, such as gradient boosting classifiers, random forests, decision trees, and support vector machines (SVM). The study examines how well these algorithms can detect and prevent zero-day attacks. To do this, we carefully prepare a dataset containing different network characteristics for analysis, ensuring that categorical variables are handled properly. We then train and test the selected algorithms using this dataset. Based on the data, random forest outperforms the other algorithms in terms of detection rates and accuracy. This is due to the fact that random forest's ability to recognize intricate patterns linked to zero-day assaults is enhanced by its continuous learning of weaker models. The results demonstrate how machine learning may be used to improve cybersecurity defenses against new threats like zero-day assaults. The CSE-CIC-IDS2018 Dataset was used in the study's execution and assessment.


Keywords


CSECICIDS2018 Dataset; Machine Learning; Random Forest; Zero-day attack.

Full Text:

PDF

References


Ahsan, M., Nygard, K. E., Gomes, R., Chowdhury, M. M., Rifat, N., & Connolly, J. F. (2022). Cybersecurity threats and their mitigation approaches using Machine Learning—A Review. Journal of Cybersecurity and Privacy, 2(3), 527-555. https://doi.org/10.3390/jcp2030027

Aslan, Ö., Aktuğ, S. S., Ozkan-Okay, M., Yilmaz, A. A., & Akin, E. (2023). A comprehensive review of cyber security vulnerabilities, threats, attacks, and solutions. Electronics, 12(6), 1333. http://dx.doi.org/10.3390/electronics12061333

Azam, Z., Islam, M. M., & Huda, M. N. (2023). Comparative analysis of intrusion detection systems and machine learning based model analysis through decision tree. IEEE Access. http://dx.doi.org/10.1109/ACCESS.2023.3296444

Guo, Y. (2023). A review of Machine Learning-based zero-day attack detection: Challenges and future directions. Computer communications, 198, 175-185. https://doi.org/10.1016/j.comcom.2022.11.001

Hamid, K., Iqbal, M. W., Aqeel, M., Liu, X., & Arif, M. (2022, December). Analysis of Techniques for Detection and Removal of Zero-Day Attacks (ZDA). In International Conference on Ubiquitous Security (pp. 248-262). Singapore: Springer Nature Singapore. http://dx.doi.org/10.1007/978-981-99-0272-9_17

Kasowaki, L., & Deniz, E. (2024). Securing the Future: Strategies and Technologies for Cyber Protection (No. 11704). EasyChair. https://easychair.org/publications/preprint/zwVJ

Kaur, R., & Singh, M. (2015). A hybrid real-time zero-day attack detection and analysis system. International Journal of Computer Network and Information Security, 7(9), 19-31. http://dx.doi.org/10.5815/ijcnis.2015.09.03

Khan, M., & Ghafoor, L. (2024). Adversarial Machine Learning in the Context of Network Security: Challenges and Solutions. Journal of Computational Intelligence and Robotics, 4(1), 51-63. https://thesciencebrigade.com/jcir/article/view/118

Kumar, V., & Sinha, D. (2021). A robust intelligent zero-day cyber-attack detection technique. Complex & Intelligent Systems, 7(5), 2211-2234. https://link.springer.com/article/10.1007/s40747-021-00396-9

Kunwar S. V., and Reenu S., (2014). Analyzing of Zero Day Attack and its Identification Techniques. February 2014. https://www.researchgate.net/publication/260489192_Analyzing_of_Zero_Day_Attack_and_its_Identification_Techniques

Rahul, Priyansh K.,Subrat S., and Monika (2020). Analysis of machine learning models for malware detection. Journal of Discrete Mathematical Sciences and Cryptography 23(2):395-407. https://doi.org/10.1080/09720529.2020.1721870

Sayadi, H. (2023). ADVANCING HARDWARE-ASSISTED CYBERSECURITY: EFFECTIVE MACHINE LEARNING APPROACHES FOR ZERO-DAY MALWARE DETECTION (Doctoral dissertation, California State University, Fullerton).

Strielkowski, W., Vlasov, A., Selivanov, K., Muraviev, K., & Shakhnov, V. (2023). Prospects and challenges of the machine learning and data-driven methods for the predictive analysis of power systems: A review. Energies, 16(10), 4025. https://doi.org/10.3390/en16104025

Thakur, M. (2024). Cyber Security Threats and Countermeasures in Digital Age. Journal of Applied Science and Education (JASE), 1-20. http://dx.doi.org/10.3844/jcssp.2023.20.56

Yuxin D., Sheng C., Jun X. (2016). Application of Deep Belief Networks for opcode based malware detection. Conference: 2016 International Joint Conference on Neural Networks (IJCNN) July, 2016. http://dx.doi.org/10.1109/IJCNN.2016.7727705

Zoppi, T., Ceccarelli, A., & Bondavalli, A. (2021). Unsupervised algorithms to detect zero-day attacks: Strategy and application. Ieee Access, 9, 90603-90615. https://doi.org/10.1109/ACCESS.2021.3090957




DOI: https://doi.org/10.17509/jcs.v5i1.70795

Refbacks

  • There are currently no refbacks.